Processes and systems for glass making can utilize heat recovery to improve operational efficiency and flexibility of operation to provide improved yield, higher quality, or more consistent quality glass, and/or other efficiencies. Some embodiments can utilize adjustments in burner operation to account for different manufacturing conditions to provide improved quality of fabricated glass to provide improved yields of glass with a more efficient utilization of heat, which can improve the environmental impact associated with the manufacturing process in addition to improving the operational efficiency and flexibility of the glass manufacturing process.

Processes and systems for glass making can utilize heat recovery to improve operational efficiency and flexibility of operation to provide improved yield, higher quality, or more consistent quality glass, and/or other efficiencies. Some embodiments can utilize adjustments in burner operation to account for different manufacturing conditions to provide improved quality of fabricated glass to provide improved yields of glass with a more efficient utilization of heat, which can improve the environmental impact associated with the manufacturing process in addition to improving the operational efficiency and flexibility of the glass manufacturing process.

Disclosed is an electronic device for implementing a temperature prediction and control system. The electronic device includes a communication interface, a memory in which a trained first neural network model and a trained second neural network model are stored, and one or more processors configured to perform preprocessing, when process information including fuel input information for a glass melting device is received through the communication interface, on the received process information, input the preprocessed process information into the trained first neural network model to obtain first predicted temperature information corresponding to a first position of the glass melting device, input the obtained first predicted temperature information and the process information into the trained second neural network model obtain second predicted temperature information corresponding to a second position of the glass melting device, and provide guidance information including the obtained first predicted temperature information and the obtained second predicted temperature information.

Disclosed is an electronic device for implementing a temperature prediction and control system. The electronic device includes a communication interface, a memory in which a trained first neural network model and a trained second neural network model are stored, and one or more processors configured to perform preprocessing, when process information including fuel input information for a glass melting device is received through the communication interface, on the received process information, input the preprocessed process information into the trained first neural network model to obtain first predicted temperature information corresponding to a first position of the glass melting device, input the obtained first predicted temperature information and the process information into the trained second neural network model obtain second predicted temperature information corresponding to a second position of the glass melting device, and provide guidance information including the obtained first predicted temperature information and the obtained second predicted temperature information.

Systems, methods, and computer program products are provided for automatic tweel control in molten glass manufacturing. An example system includes a processor configured to receive visual data from a camera positioned with a view of a molten glass flow that is spreading from a melting tank into a bath containing molten metal, wherein a flow rate of the molten glass flow is controlled by a tweel. The processor is also configured to process the visual data to determine a value of a dimension of the molten glass flow. The processor is further configured to, in response to the value of the dimension of the molten glass flow satisfying a predetermined threshold value, generate a first control pulse signal to the tweel, wherein the first control pulse signal is configured to incrementally increase or decrease the flow rate of the molten glass flow.

Systems, methods, and computer program products are provided for automatic tweel control in molten glass manufacturing. An example system includes a processor configured to receive visual data from a camera positioned with a view of a molten glass flow that is spreading from a melting tank into a bath containing molten metal, wherein a flow rate of the molten glass flow is controlled by a tweel. The processor is also configured to process the visual data to determine a value of a dimension of the molten glass flow. The processor is further configured to, in response to the value of the dimension of the molten glass flow satisfying a predetermined threshold value, generate a first control pulse signal to the tweel, wherein the first control pulse signal is configured to incrementally increase or decrease the flow rate of the molten glass flow.

Method for removing bubbles from a molten substrate. The molten substrate from a furnace passes through a downtube to reach additional manufacturing tools, such as an extrusion bushing. One or more ultrasonic sensors are arranged along the downtube. The ultrasonic sensor(s) transmit ultrasonic energy into the molten substrate and measure a characteristic of the ultrasonic energy, such as a propagation time for the ultrasonic energy to be reflected back to the ultrasonic sensor(s). A bubble is detected when a change in the Characteristic of the ultrasonic energy is detected. When a bubble is detected, flow through the downtube is diverted to a duct to remove a slug of molten substrate that includes the bubble.

Method for removing bubbles from a molten substrate. The molten substrate from a furnace passes through a downtube to reach additional manufacturing tools, such as an extrusion bushing. One or more ultrasonic sensors are arranged along the downtube. The ultrasonic sensor(s) transmit ultrasonic energy into the molten substrate and measure a characteristic of the ultrasonic energy, such as a propagation time for the ultrasonic energy to be reflected back to the ultrasonic sensor(s). A bubble is detected when a change in the Characteristic of the ultrasonic energy is detected. When a bubble is detected, flow through the downtube is diverted to a duct to remove a slug of molten substrate that includes the bubble.

The present invention relates to a submerged combustion furnace for melting ceramic frits by means of a submerged combustion process, said furnace comprising at least one control loop with feedback of the overall weight regulating at least one process variable of the furnace for producing ceramic frit.

The invention also relates to a regulating method for a submerged combustion furnace having these features, whereby obtaining a batch production of a ceramic frit having certain characteristics. The regulating method is implemented in the system by means of regulating process variables relating to the production of molten material during production.

Controlling foam in apparatus downstream of a melter by adjustment of alkali oxide content in the melter. One method includes feeding a feedstock into a submerged combustion melter (SCM) apparatus having an internal space containing a flowing or non-flowing molten mass of foamed glass comprising molten glass and bubbles entrained therein, the molten mass having glass foam comprising glass foam bubbles on at least a portion of a top surface of the molten mass. The molten mass from the SCM is routed to a downstream apparatus, stability of the glass foam in the downstream apparatus is observed, and alkali oxide percentage fed to the SCM apparatus is adjusted based on the observation to positively or negatively affect the foam stability. Systems for carrying out the methods, and the products of the methods are also considered novel and inventive.